Newly Accepted

A web-based multi-model comparison of procedural medieval castle worlds made with three.js. It showcases the same castle brief across eight models and three art directions, with static gallery previews and full-page worlds you can open.

A developer profile platform that pulls in contributions from external sources and adds an embedded AI hypeman for answering questions about your profile. It also offers developer APIs for using the profile data in other apps.

A Claude Code skill that searches royalty-free stock photos through the Pexels API, with install and usage instructions in the repo.

A private AI meeting-notes app that transcribes calls locally and uses Codex, Claude Code, or a local LLM to generate summaries and action items on-device.

A local-first AI reading assistant for Chrome that rewrites pages into customizable briefs, supports reusable reading recipes, and can run with local or hosted models.

Local codebase indexer and MCP server for Claude Code that watches project files, builds a private index on-device, and serves relevant snippets to Claude and other MCP clients.

AI-powered mock interview tool that generates role-specific questions from your CV and job description, scores answers, and gives concrete feedback and rewrites.

AI Buddy is a free macOS menu-bar app for screenshots and voice dictation. It lets users capture regions, windows, or full screen, copy instantly to clipboard, and transcribe speech to text using Gemini 3.5 Flash.

Google Research paper describing a deployed multimodal defense system for detecting coordinated synthetic spam and abusive media at scale, using account relatedness, synthetic content classification, and LoRA-tuned LLMs.

A deterministic multi-agent workflow runtime for GPT/Codex with branching, retries, resumability, structured outputs, and parallel fan-out. The README shows install and run instructions plus a concrete workflow example.

Aloud is a macOS tool that reads Claude Code and OpenAI Codex replies out loud using local text-to-speech. It includes session-level controls, keyboard shortcuts, hook integration, and a clear install flow for developers.

PilotCite is an AI visibility monitoring platform for tracking how brands appear in responses from tools like ChatGPT, Gemini, Perplexity, Claude, Copilot, and Grok. It combines citation tracking, competitor benchmarking, site audits, prompt research, and content generation in one dashboard.

Shikigami is a desktop agentic IDE for running multiple coding agents in parallel, each in its own isolated git worktree. It supports Claude Code and OpenAI Codex, keeps sessions resumable, and includes built-in review tools like an editor, terminals, source control, databases, and Docker.

A step-by-step guide for turning a spare Mac into an always-on machine Claude Code can control over SSH or from the Claude app.

A browser strategy game where you run a frontier AI lab, manage compute markets and research paths, and race rival labs to build AGI. It includes weekly Easy and Hard challenges plus a replay-verified leaderboard.

An open-sourced pipeline that uses Gemini, GoPro footage, Garmin .fit telemetry, Strava segments, and manual labels to automatically build cycling highlight reels.

A browser-based AI music generator that creates songs, instrumentals, beats, hooks, and background music from prompts, lyrics, and style tags. The page also includes example tracks, usage guidance, FAQ content, and pricing/credit details.

Open-source family AI agent for the home, built to run on a wall-mounted Android phone. The project positions itself as a shared household assistant for shopping lists, calendars, timers, reminders, expenses, and approved family calling.

A terminal coding agent for Mac that runs on local models through MLX, edits code, runs tests, and keeps everything on-device.

An AI strategy benchmark that pits frontier language models against each other in turn-based games and records decision logs and raw replays.

Traicer is a developer tool that captures selected AI coding conversations, redacts secrets, encrypts traces, and stores them in seller-controlled S3-compatible storage for later marketplace use.

BOUND is a deterministic control harness for AI agents. It sits between agent execution and the next decision, using observable evidence to choose ACCEPT, RETRY, REPLAN, or ROLLBACK.

Open-source tool for removing refusal behavior from open-weight transformer language models by identifying and orthogonalizing refusal directions in activation space.

Open-source social media skills for AI agents that generate platform-native posts, threads, carousels, replies, ad copy, and content calendars in a brand voice.